Meeting Banner
Abstract #2253

Tumour relapse prediction using multi-parametric MR data recorded during follow-up of GBM patients

Adrian Ion-Margineanu 1,2 , Sofie Van Cauter 3 , Diana M Sima 1,2 , Frederik Maes 2,4 , Stefaan W Van Gool 5 , Stefaan Sunaert 3 , Uwe Himmelreich 6 , and Sabine Van Huffel 1,2

1 STADIUS, KU Leuven - ESAT, Leuven, Belgium, Belgium, 2 iMinds Medical IT, Leuven, Belgium, 3 Department of Radiology, University Hospitals of Leuven, Leuven, Belgium, 4 PSI, KU Leuven - ESAT, Belgium, 5 Department of Pedriatic Neuro-oncology, University Hospitals of Leuven, Belgium, 6 Department of Imaging and Pathology - Biomedical MRI/ MoSAIC, KU Leuven, Belgium

Our study is trying to find a relation between multi-parametric MR data (T1 post contrast - MRI, T2* - MRI, FLAIR, Perfusion MRI, Diffusion MRI, MR Spectroscopy) acquired during the follow-up of 29 glioblastoma multiforme (GBM) patients and the relapse of the brain tumour after surgery, as described by the clinically accepted RANO criteria. We find that ensemble classifiers can accurately predict the outcome of the therapy with approximately one month in advance before doctors. The same results were found also when using just perfusion features.

This abstract and the presentation materials are available to members only; a login is required.

Join Here